core.py

import pandas as pd
import yaml, datetime, hashlib, json
import math
from pathlib import Path
from templating import get_env, render
from models import CompanyMeta, ReportSections, RenderPayload
from render import html_to_pdf, html_to_docx

DISPLAY_NAME = {
    "co2_emissions": "CO₂排出量",
    "energy_renewable_ratio": "再生可能エネルギー比率",
    "female_management_ratio": "女性管理職比率",
}

def _sha256(p: Path) -> str:
    h = hashlib.sha256()
    with p.open("rb") as f:
        for chunk in iter(lambda: f.read(8192), b""):
            h.update(chunk)
    return h.hexdigest()

def _require_columns(df: pd.DataFrame, required, name: str):
    missing = [c for c in required if c not in df.columns]
    if missing:
        raise ValueError(f"{name} に必須列がありません: {missing}. 例: {required}")

def load_company_meta(path: str) -> CompanyMeta:
    data = yaml.safe_load(Path(path).read_text(encoding="utf-8"))
    return CompanyMeta(**data)

def load_financials(path: str) -> pd.DataFrame:
    df = pd.read_csv(path)
    _require_columns(
        df,
        ["year", "quarter", "revenue", "ebit", "net_income", "total_assets", "total_equity"],
        "financials.csv",
    )
    
    df["year"] = pd.to_numeric(df["year"], errors="coerce").astype("Int64")
    q = (
        df["quarter"]
        .astype(str).str.upper()
        .str.replace("Ｑ", "Q")
        .str.replace(" ", "")
    )
    df["quarter"] = "Q" + q.str.extract(r"(\d)", expand=False).fillna("")
    return df

def load_esg(path: str) -> pd.DataFrame:
    df = pd.read_csv(path)
    _require_columns(df, ["year", "metric", "value", "unit", "scope", "notes"], "esg_metrics.csv")
    df["year"] = pd.to_numeric(df["year"], errors="coerce").astype("Int64")
    return df

def compute_kpi(fin_df: pd.DataFrame, fiscal_year: int):
    years = set(fin_df["year"].dropna().astype(int))
    if fiscal_year not in years:
        raise ValueError(f"financials.csv に年度 {fiscal_year} のデータがありません。year 列を確認してください。")

    fy = fin_df[fin_df["year"] == fiscal_year].copy()
    if fy.empty:
        raise ValueError(f"年度 {fiscal_year} の四半期データが空です。quarter の表記（Q1～Q4）を確認してください。")

    order = {"Q1": 1, "Q2": 2, "Q3": 3, "Q4": 4}
    fy["q_order"] = fy["quarter"].map(order)
    latest = fy.sort_values("q_order").dropna(subset=["q_order"]).tail(1)
    if latest.empty:
        raise ValueError(f"年度 {fiscal_year} の quarter が Q1〜Q4 として認識できません。例: Q4")

    prev_fy = fin_df[fin_df["year"] == fiscal_year - 1].copy()
    if not prev_fy.empty:
        prev_fy["q_order"] = prev_fy["quarter"].map(order)
        prev = prev_fy.sort_values("q_order").dropna(subset=["q_order"]).tail(1)
    else:
        prev = pd.DataFrame()

    revenue = float(latest["revenue"].iloc[0])
    ebit = float(latest["ebit"].iloc[0])
    net_income = float(latest["net_income"].iloc[0])
    equity = float(latest["total_equity"].iloc[0]) if "total_equity" in latest else 0.0

    ebit_margin = (ebit / revenue * 100) if revenue else 0.0
    roe = (net_income / equity * 100) if equity else 0.0
    revenue_yoy = 0.0
    if not prev.empty and float(prev["revenue"].iloc[0]) != 0:
        revenue_yoy = ((revenue / float(prev["revenue"].iloc[0])) - 1) * 100

    return {
        "revenue": revenue,
        "ebit": ebit,
        "net_income": net_income,
        "ebit_margin": ebit_margin,
        "roe": roe,
        "revenue_yoy": revenue_yoy,
    }

def esg_table(df: pd.DataFrame, fiscal_year: int):
    dfy = df[df["year"] == fiscal_year].copy()
    rows = []
    for _, r in dfy.iterrows():
        metric = r["metric"]
        display = DISPLAY_NAME.get(metric, metric)
        rows.append({
            "display": display,
            "value": r["value"],
            "unit": r.get("unit", ""),
            "notes": r.get("notes", ""),
        })
    return rows

def build_sections(meta: CompanyMeta, kpi: dict, esg_rows: list, llm=None) -> ReportSections:
    if llm:
        ceo_message = llm.generate_ceo_message(meta, kpi, esg_rows)
        risk = llm.generate_risk_opportunity(meta, kpi, esg_rows)
    else:
        ceo_message = f"{meta.fiscal_year}期は、売上成長と収益性の両立に注力しました。"
        risk = "主要リスクはマクロ環境と規制動向。機会は生成AI活用と脱炭素需要の拡大です。"
    return ReportSections(ceo_message=ceo_message, risk_opportunity=risk)


def _s(x):
    if x is None:
        return ""
    if isinstance(x, float) and math.isnan(x):
        return ""
    return str(x)

def _translate_payload_texts(payload: dict, lang: str, llm):
    if not llm or lang == "ja":
        return payload

    texts = []
    texts.append(_s(payload["sections"]["ceo_message"]))
    texts.append(_s(payload["sections"]["risk_opportunity"]))
    # esg_table display/notes
    for row in payload["esg_table"]:
        texts.append(_s(row.get("display", "")))
        texts.append(_s(row.get("notes", "")))
    texts.append(_s(payload["meta"]["report_title"]))
    for topic in payload["meta"].get("material_topics", []):
        texts.append(_s(topic))

    translated = llm.translate_texts(texts, target_lang=lang)
    it = iter(translated)

    payload["sections"]["ceo_message"] = next(it)
    payload["sections"]["risk_opportunity"] = next(it)
    for row in payload["esg_table"]:
        row["display"] = next(it)
        row["notes"] = next(it)
    payload["meta"]["report_title"] = next(it)
    mt = payload["meta"].get("material_topics", [])
    for i in range(len(mt)):
        mt[i] = next(it)

    return payload
def generate_report(
    company_yaml,
    financials_csv,
    esg_csv,
    templates_dir,
    template_name="report.html.j2",
    out_html="output/report.html",
    out_pdf="output/report.pdf",
    out_docx="output/report.docx",
    lang="ja",
    llm=None,
):
    Path(Path(out_html).parent).mkdir(parents=True, exist_ok=True)
    tdir = Path(templates_dir)
    tdir.mkdir(parents=True, exist_ok=True)
    tpl = tdir / template_name
    if not tpl.exists():
        tpl.write_text("""<!doctype html>
<html lang="{{ lang }}">
<head>
  <meta charset="utf-8" />
  <title>{{ meta.report_title }} - {{ meta.company_name }}</title>
  <style>
    body { font-family: system-ui, -apple-system, "Segoe UI", Helvetica, Arial; line-height: 1.6; }
    h1,h2,h3 { margin: 0.6em 0; }
    .kpi { display: grid; grid-template-columns: repeat(3, 1fr); gap: 12px; }
    .card { border: 1px solid #ddd; border-radius: 12px; padding: 12px; }
    .small { color: #666; font-size: 0.9em; }
    table { border-collapse: collapse; width: 100%; }
    th, td { border: 1px solid #eee; padding: 8px; text-align: right; }
    th { background: #fafafa; }
    .left { text-align: left; }
  </style>
</head>
<body>
  <h1>{{ meta.report_title }}（{{ meta.fiscal_year }}）</h1>
  <p class="small">{{ meta.company_name }} / Ticker: {{ meta.ticker }} / 通貨: {{ meta.currency }}</p>

  <h2>CEOメッセージ</h2>
  <p>{{ sections.ceo_message }}</p>

  <h2>ハイライトKPI</h2>
  <div class="kpi">
    <div class="card">
      <div class="small">売上高</div>
      <div><strong>{{ kpi.revenue | round(0) | int }} {{ meta.currency }}</strong></div>
      <div class="small">前年比: {{ kpi.revenue_yoy | round(1) }}%</div>
    </div>
    <div class="card">
      <div class="small">EBIT</div>
      <div><strong>{{ kpi.ebit | round(0) | int }} {{ meta.currency }}</strong></div>
      <div class="small">マージン: {{ kpi.ebit_margin | round(1) }}%</div>
    </div>
    <div class="card">
      <div class="small">純利益</div>
      <div><strong>{{ kpi.net_income | round(0) | int }} {{ meta.currency }}</strong></div>
      <div class="small">ROE: {{ kpi.roe | round(1) }}%</div>
    </div>
  </div>

  <h2>ESGサマリー</h2>
  <table>
    <thead>
      <tr><th class="left">指標</th><th>値</th><th>単位</th><th class="left">備考</th></tr>
    </thead>
    <tbody>
      {% for row in esg_table %}
      <tr>
        <td class="left">{{ row.display }}</td>
        <td>{{ row.value }}</td>
        <td>{{ row.unit }}</td>
        <td class="left">{{ row.notes }}</td>
      </tr>
      {% endfor %}
    </tbody>
  </table>

  <h2>リスク & 機会（要約）</h2>
  <p>{{ sections.risk_opportunity }}</p>

  <footer class="small">Generated on {{ generated_at }}</footer>
</body>
</html>
""", encoding="utf-8")

    meta = load_company_meta(company_yaml)
    fin = load_financials(financials_csv)
    esg = load_esg(esg_csv)

    kpi = compute_kpi(fin, meta.fiscal_year)
    esg_rows = esg_table(esg, meta.fiscal_year)
    sections = build_sections(meta, kpi, esg_rows, llm=llm)

    env = get_env(templates_dir)
    payload = RenderPayload(
        meta=meta,
        esg_table=esg_rows,
        kpi=kpi,
        sections=sections,
        generated_at=datetime.datetime.now().strftime("%Y-%m-%d %H:%M"),
        lang=lang,
    ).model_dump()

    payload = _translate_payload_texts(payload, lang=lang, llm=llm)

    html = render(env, template_name, payload)
    Path(out_html).write_text(html, encoding="utf-8")
    html_to_pdf(html, out_pdf)
    html_to_docx(html, out_docx)

    meta_json = {
        "inputs": {
            "company_yaml_sha": _sha256(Path(company_yaml)),
            "financials_csv_sha": _sha256(Path(financials_csv)),
            "esg_csv_sha": _sha256(Path(esg_csv)),
            "lang": lang,
        },
        "outputs": {"html": out_html, "pdf": out_pdf, "docx": out_docx},
        "template": {"dir": templates_dir, "name": template_name},
        "generated_at": datetime.datetime.now().isoformat(timespec="seconds"),
    }
    return out_html, out_pdf, out_docx, meta_json